A personalized design method for 3D printed products based on 3D scanning human body model

Abstract

The present invention relates to the field of three-dimensional scanning technology, and in particular to a method for personalized design of 3D printed products based on a three-dimensional scanned human body model. The method comprises the following steps: obtaining three-dimensional scanning data of the human body and human body composition data; performing movable joint analysis on the three-dimensional scanning data of the human body to generate movable joint data of the human body; performing distributed three-dimensional model modeling on the three-dimensional scanning data of the human body based on the movable joint data of the human body to generate a three-dimensional model of the human body; performing initial human body fitting product design on the three-dimensional model of the human body based on 3D printing technology to obtain initial 3D printed product parameter data. The present invention optimizes the fit and personalized design accuracy of 3D printed products by combining human joints, body composition data and user feedback, thereby improving the accuracy and flexibility of personalized design of 3D printed products.

Description

Technical Field

[0001] The present invention relates to the field of three-dimensional scanning technology, and in particular to a personalized design method for 3D printed products based on a three-dimensional scanning human body model. Background Art

[0002] The earliest 3D scanning technology was applied to industrial inspection. With the development of computer vision, laser and optical technology, high-precision scanning of the human body has gradually been achieved. This technological breakthrough provides more accurate three-dimensional data models for the medical, sports science and clothing industries. In recent years, with the popularization of consumer-grade 3D scanning equipment, ordinary users can also obtain their own three-dimensional models, which has promoted the demand and development of personalized design. In personalized product design, 3D scanning data is used to generate designs that conform to personal body characteristics, thereby greatly improving the comfort and user experience of the product. For example, in the medical field, 3D printing based on scanned models of bones, joints, etc. can provide personalized medical devices; in fashion and footwear design, based on the scanned models of the user's feet and body shape, products that meet personal size can be accurately customized. With the advancement of deep learning and artificial intelligence, the accuracy of data processing and modeling has been improved, making the design process based on 3D scanning more efficient. However, the current traditional methods lack in-depth analysis of the user's physiological characteristics (such as body composition), resulting in limited customization effects. At the same time, defects such as insufficient materials and morphological errors often occur in 3D printed products, affecting the user experience, resulting in low accuracy and flexibility in personalized design of 3D printed products. Summary of the invention

[0003] Based on this, it is necessary to provide a personalized design method for 3D printed products based on a three-dimensional scanning human body model to solve at least one of the above technical problems.

[0004] To achieve the above object, a 3D printed product personalized design method based on a 3D scanned human body model is provided, the method comprising the following steps:

[0005] Step S1: acquiring human body 3D scanning data and human body composition data; performing movable joint analysis on the human body 3D scanning data to generate human body movable joint data; performing distributed 3D modeling on the human body 3D scanning data based on the human body movable joint data to generate a human body 3D model;

[0006] Step S2: Based on the 3D printing technology, an initial human body fitting product design is performed on the human body three-dimensional model to obtain initial 3D printing product parameter data; the human body composition data is used to perform posture coordination analysis on the human body three-dimensional model to generate human body coordination data; the human body coordination data is imported into the initial 3D printing product parameter data to adjust the fitting morphological parameters to generate 3D printing product visualization data;

[0007] Step S3: collecting user feedback on the 3D printed product visualization data to obtain user feedback data; modifying the changed part parameters of the 3D printed product visualization data according to the user feedback data, thereby generating a local part change model; replacing the local part change model with the 3D printed product visualization data, thereby generating personalized 3D printed product visualization data;

[0008] Step S4: performing printing simulation defect location on the personalized 3D printed product visualization data to generate product defect location data; adjusting the printing material of the personalized 3D printed product visualization data according to the product defect location data to generate personalized 3D printed product material adjustment data; performing virtual reality enhancement on the personalized 3D printed product visualization data based on the personalized 3D printed product material adjustment data to generate a personalized 3D printed product design visualization interface to execute the 3D printed product personalized design operation.

[0009] The present invention enables the product to accurately adapt to the individual's body shape and range of joint motion by personalized modeling of human three-dimensional scanning data. This highly customized design improves the comfort and fit of the product and meets the user's demand for personalized products. Through the body composition analysis of electrical impedance data and the personalized three-dimensional model adjustment, the structure of the product can adapt to individual differences and ensure the best performance and support in actual use. This precise design method improves the functionality and durability of the product. Distributed modeling and automated fitting morphological parameter adjustment make the design process more efficient. Through the automatic adjustment and simulation of 3D printing product parameters, the errors of manual adjustment can be effectively avoided, and the accuracy and stability of the design can be significantly improved. Through the data processing of user feedback, the local optimization and update of the product can be quickly realized, and the change requirements proposed by the user can be met in a short time. This mechanism improves the response speed of user feedback and enhances the user's sense of participation and satisfaction. Defect location and material adjustment are carried out in the printing simulation link to avoid errors and defects in actual printing, improve the success rate and reliability of printed products, and save material and time costs. The addition of virtual reality technology provides designers and users with a more intuitive interactive experience, allowing users to fully understand and verify the design effect before printing, and further optimize the final effect of personalized products. Product design and simulation completed in a virtual environment reduces unnecessary physical sample production and resource waste, reduces design and production costs, and improves environmental protection. The automation, efficiency and accuracy of this process make the product design and manufacturing process more competitive, and can launch personalized products that meet user needs more quickly, thereby enhancing the brand's position in the customized market. Therefore, the present invention optimizes the fit and personalized design accuracy of 3D printed products by combining human joints, body composition data and user feedback, thereby improving the accuracy and flexibility of personalized design of 3D printed products.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: obtaining three-dimensional scanning data of a human body; obtaining human body composition data using a body composition calculation formula;

[0012] Step S12: performing data preprocessing on the human body three-dimensional scanning data to generate standard human body three-dimensional scanning data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization;

[0013] Step S13: performing movable joint analysis on the standard human body three-dimensional scanning data to generate human body movable joint data; performing human body part division on the standard human body three-dimensional scanning data based on the human body movable joint data to generate human body part division data;

[0014] Step S14: Perform distributed 3D modeling on the standard human body 3D scanning data using the human body part division data to generate a human body 3D model; perform 3D reconstruction on the human body 3D model using the human body composition data to generate a human body 3D model.

[0015] The present invention can ensure that the acquired three-dimensional scanning data is more accurate and consistent through data preprocessing in step S12, including data cleaning, denoising, missing value filling and standardization, and provide a reliable basis for subsequent analysis and modeling. The analysis of the movable joints of the human body in step S13 helps to extract the kinematic characteristics of the human body and accurately identify the range of motion and flexibility of the human body. This is of great significance for personalized health monitoring, rehabilitation training and motion analysis. By dividing the human body into parts based on the data of movable joints of the human body (step S13), different parts of the human body (such as head, upper limbs, lower limbs, etc.) can be clearly defined, providing structured data support for subsequent posture analysis, personalized model creation and ergonomic research. In step S14, large-scale three-dimensional human body data can be better processed through distributed three-dimensional model modeling. This process can not only improve the modeling efficiency, but also generate a three-dimensional human body model with higher accuracy and operability, which is suitable for applications such as virtual reality, medical imaging, and personalized wearable devices.

[0016] Preferably, the formula for calculating body composition in step S11 is as follows:

[0017]

[0018] In the formula, Expressed as lean body mass, Expressed as the maximum measurement frequency, Expressed as the impedance weighting coefficient, Represents the human body at frequency The impedance value below Expressed as the height weighting coefficient, is the height of the individual, Expressed as the weight-frequency weighting coefficient, is the weight of the individual, Expressed as the age weighted coefficient, is represented as an exponential decay term of age, is the individual age, Expressed as an exponent. Expressed as the age exponential decay coefficient.

[0019] The present invention analyzes and integrates a body composition calculation formula. The principle of the formula is that different tissues in the human body (such as fat, muscle, water, etc.) have different electrical conductivities, so the body composition can be inferred by measuring electrical impedance. For example, tissues with high water content (such as muscle) have lower electrical impedance, while fat tissue has higher electrical impedance due to its low water content. Through multi-frequency measurement, the penetration depth and response characteristics of currents of different frequencies make the electrical impedance data more comprehensive. Combined with individual information such as height, weight, and age, the formula balances multiple weighted items and accumulates integrals to produce a more reliable estimate of lean body mass. At the frequency The measured electrical impedance It reflects the distribution of water and highly conductive tissues such as muscles in the body. Weighted, significantly affecting the contribution of water and muscle to lean body mass. The weighting of water and muscle content is significant, the formula is more sensitive to highly conductive tissues, and the resulting lean body mass estimate is more accurate, especially for individuals with a greater influence of water content (such as athletes). Height squared term Simulates the size of the body surface area and adjusts the impedance results based on the surface area. A larger body surface area generally means a higher overall mass. Adjusting the calculation of lean body mass based on body surface area enhances the formula's adaptability to individuals of different heights, allowing it to maintain accuracy in a variety of body types. With measurement frequency The logarithmic relationship of reflects the influence of body weight on the overall conductivity and frequency response. The importance of this control. The logarithmic frequency term helps to smooth the response variation at different frequencies, reduce the influence of frequency extremes, and make the body composition estimate more robust to different frequencies. It is particularly useful for deriving balanced body composition results from multi-frequency data. The exponential decay term describes the natural decay effect of age on body composition (especially lean body mass), which is expressed by and Control its intensity. The older the age, the more significant this attenuation is. The nonlinear attenuation of age takes into account the natural trend of muscle and water content decreasing with age. In this way, the formula maintains accuracy at all ages and effectively avoids errors caused by ignoring the age factor. When using the conventional body composition calculation formula in the field, the fat-free body mass can be obtained. By applying the body composition calculation formula provided by the present invention, the fat-free body mass can be calculated more accurately. The formula integrates impedance data of different frequencies through integral operations, effectively utilizing the characteristics of low frequency penetrating the fat layer and high frequency penetrating cells, making the formula more in-depth and broad when estimating body composition. By weighted control of individual height, weight, and age, the formula is more adaptable to different body shapes and age groups, and the estimated results are more in line with the actual physiological state. Multiple weighted parameter controls enable the formula to accurately adjust the weights of each influencing factor. Compared with simple formulas, this complex formula shows higher accuracy in a wider range of people.

[0020] Preferably, the distributed 3D modeling of the standard human body 3D scan data by using the human body part division data comprises the following steps:

[0021] Calculating the area of ​​the human body part division data to obtain the area data; performing regional segmentation on the standard human body three-dimensional scanning data based on the area data to generate human body part regional segmentation data, wherein the human body part segmentation data includes main part regional segmentation data and secondary part regional segmentation data;

[0022] Assigning a high modeling priority to the main part region segmentation data and a low modeling priority to the secondary part region segmentation data, thereby obtaining part region modeling priority data, and performing distributed computing node allocation on the human body part region segmentation data according to the part region modeling priority data, thereby generating distributed region modeling data;

[0023] Perform local modeling on the distributed regional modeling data to generate a local three-dimensional model of the human body part; confirm the part connection points of the local three-dimensional model of the human body part to obtain the part connection center point data; and splice the local three-dimensional model of the human body part according to the part connection center point data to generate a three-dimensional model of the human body.

[0024] The present invention can more accurately determine the proportion and importance of different parts of the human body through the part area calculation in step S141, thereby performing reasonable regional segmentation on the standard human body three-dimensional scanning data. This segmentation not only provides a clear framework for subsequent modeling, but also generates segmentation data of the main part area and the secondary part area according to the characteristics of different parts, which is conducive to more refined modeling. Step S142 improves the modeling efficiency by assigning high modeling priority to the main part area and low modeling priority to the secondary part area. Prioritizing important parts can ensure the accuracy and expressiveness of the model, while reducing the processing time of secondary parts, thereby optimizing the entire modeling process. By allocating distributed computing nodes according to the part area modeling priority data, step S142 effectively utilizes distributed computing resources and significantly accelerates the modeling process of the human body three-dimensional model. In particular, when facing complex three-dimensional data, distributed computing can improve efficiency and reduce resource usage. In step S143, local modeling helps to establish three-dimensional models of various parts in advance to ensure the accuracy of each part. Through the confirmation of the part connection point, the continuity between parts and the coordination of the overall structure can be maintained in the subsequent model splicing. The final complete human 3D model can achieve more accurate human representation and is suitable for virtual reality, medical imaging, motion analysis and other fields. This process can generate a high-quality 3D human model that not only has high modeling accuracy but also good operability, especially in refined operations (such as virtual testing, personalized customization and treatment planning).

[0025] Preferably, confirming the connection points of the local three-dimensional model of the human body part includes:

[0026] Extracting the part boundary point set from the local three-dimensional model of the human body part to obtain the part boundary point set; performing boundary detection on the part boundary point set to generate potential connection point data of the part boundary;

[0027] The distance between the boundary points of adjacent parts of the local three-dimensional model of the human body parts is calculated by using the potential connection point data of the boundary of the parts to obtain the distance data of the boundary points of adjacent parts; the distance data of the boundary points of adjacent parts is compared with the preset standard boundary point distance threshold, and when the distance data of the boundary points of adjacent parts is less than or equal to the preset standard boundary point distance threshold, the overlapping boundary point area is screened based on the distance data of the boundary points of adjacent parts to obtain the overlapping boundary point area data of adjacent parts;

[0028] The data of the overlapping boundary points of adjacent parts are distributed with part connection points to generate the spatial distribution data of the part connection points; the coordinates of the center points of the connected areas of the overlapping boundary points of adjacent parts are calculated through the spatial distribution data of the part connection points to generate the data of the part connection center points.

[0029] The present invention can accurately identify the boundary area of ​​each part by extracting the part boundary point set from the local three-dimensional model of the human body part, and provide basic data for the subsequent confirmation of the connection points. The potential connection point data of the part boundary generated by the boundary detection can further identify the connection area, thereby laying the foundation for the accurate splicing between the parts. By calculating the distance between the boundary points of adjacent parts, it can be accurately judged whether there is a potential connection area between different parts. If the distance between the boundary points of adjacent parts is less than or equal to the preset standard threshold, it means that the connection between the two parts is relatively close, and the overlapping boundary point area can be better screened. This screening mechanism can avoid interference from irrelevant areas, thereby ensuring the accuracy of model splicing. After screening the overlapping boundary point area, the connection area of ​​the adjacent parts is further analyzed through the spatial distribution data of the part connection points, so as to determine which areas should be regarded as the connection area. This operation enhances the rationality of model splicing and ensures the natural transition and continuity of the three-dimensional model of the human body when connected. After screening the overlapping boundary point area, the connection area of ​​the adjacent parts is further analyzed through the spatial distribution data of the part connection points, so as to determine which areas should be regarded as the connection area. This operation enhances the rationality of model splicing and ensures the natural transition and continuity of the human body 3D model when connected. This series of operations can greatly improve the splicing accuracy and naturalness between the parts of the human body 3D model. Through precise calculation and spatial distribution of connection points, seamless connection between different parts can be guaranteed, thus generating a more complete and coherent 3D human body model.

[0030] Preferably, step S2 comprises the following steps:

[0031] Step S21: performing an initial human body fitting product design on the human body three-dimensional model based on 3D printing technology to obtain initial 3D printing product parameter data;

[0032] Step S22: using the human body composition data to perform posture coordination analysis on the human body three-dimensional model to generate human body posture coordination data; extracting part morphological features of the human body three-dimensional model according to the human body posture coordination data to obtain part morphological feature data;

[0033] Step S23: adjusting the product morphology parameters of the initial 3D printing product parameter data according to the part morphology feature data to generate 3D printing product morphology parameter adjustment data;

[0034] Step S24: simulating the product fit of the human body three-dimensional model through the 3D printing product morphological parameter adjustment data, thereby generating product fit simulation data; and three-dimensionally visualizing the 3D printing product morphological parameter adjustment data based on the product fit simulation data, thereby generating 3D printing product visualization data.

[0035] The present invention can generate initial 3D printing product parameter data according to the specific body shape characteristics of an individual by performing an initial human body fitting product design based on a human three-dimensional model (step S21), thereby realizing a highly customized design. This design method avoids the unsuitability of universal products and provides users with higher comfort and functionality. Through body shape coordination analysis (step S22), the system deeply explores the coordination characteristics of the human body and extracts the morphological feature data of specific parts. This analysis method effectively improves the adaptability of product design to various parts of the human body, ensuring that the functionality and aesthetics of the product are more in line with user needs. In step S23, the initial product parameters are adjusted through the part morphological feature data to achieve dynamic optimization of the product morphological parameters. This process can correct the design deviation in time, ensure that the final generated product morphological parameters are more in line with actual human needs, and improve the scientificity and accuracy of the design. The fit simulation in step S24 can comprehensively evaluate the adaptability of the product to the human body. By generating fit simulation data, designers can intuitively understand the fit effect of the product in use, and make further optimizations to reduce unnecessary trial and error costs. The final generated 3D printed product visualization data (step S24) provides an intuitive, real-time 3D view for design verification and communication, improves the efficiency of collaboration between the design team and users, simplifies the feedback process, and promotes rapid iteration of design solutions. The entire step S2 forms a closed-loop process from design to analysis, optimization, simulation, and visualization. This process greatly reduces the uncertainty of manual operation through technical means, realizes the intelligence and automation of the design process, and provides reliable data support for subsequent production.

[0036] Preferably, adjusting the product morphology parameters of the initial 3D printed product parameter data by using the part morphology feature data includes:

[0037] Defining key nodes of the body contour of the three-dimensional human body model and generating key node data of the body contour; dividing the model surface mesh of the three-dimensional human body model based on the key node data of the body contour and generating model surface mesh data;

[0038] Importing the body part morphological feature data into the human body three-dimensional model for body composition data mapping to generate body composition mapping data; using the body composition mapping data to perform body composition region association on the model surface mesh data to generate body composition region association data;

[0039] Performing mesh surface deformation analysis on the body component region association data to generate mesh surface deformation data; performing mesh node adjustment on the body component region association data according to the mesh surface deformation data to generate mesh part contour node adjustment data;

[0040] The printing level in the initial 3D printing product parameter data is adjusted through the mesh part contour node adjustment data to generate 3D printing product morphological parameter adjustment data, wherein the printing level adjustment includes muscle layer adjustment and skin layer adjustment.

[0041] The present invention defines the key nodes of the part contour of the human body three-dimensional model, and generates the key node data of the part contour, so that the design can capture the geometric details of the important characteristic parts of the human body. This process ensures the accurate adaptation of the design to the local key parts, and enhances the practicality and human body fit of the product. The surface mesh of the human body three-dimensional model is divided based on the key node data of the part contour, and the generated model surface mesh data provides a high-resolution basis for subsequent analysis. The refinement of mesh division can capture complex morphological features and provide data support for deformation analysis and parameter adjustment. The part morphological feature data is imported into the model and the body composition data is mapped to generate body composition mapping data. This process deeply combines the characteristics of the human body with the three-dimensional model, so that the design not only meets the appearance requirements, but also can be targeted to optimize the functional requirements (such as support mechanics or comfort). The body composition mapping data is used to regionally associate the model surface mesh, and the body composition regional association data is generated to ensure that the design of different regions is highly consistent with the characteristics of the human body composition (such as muscle or fat layer). This method effectively supports the independent optimization design of different functional areas and improves the practicality of the overall product. By performing mesh surface deformation analysis on body component region association data and generating mesh surface deformation data, the design can capture the impact of morphological changes on fit. The contour node adjustment data generated by mesh node adjustment based on deformation data can effectively correct potential deviations in the design and ensure the accuracy of the final model. The initial printing parameter data is adjusted at the printing level (including muscle layer and skin layer adjustment) through the mesh part contour node adjustment data, so that the design is more in line with the characteristics of the multi-level structure of the human body. This refined adjustment improves the product's performance in structure, elasticity and comfort, and makes the printed product have better fit and functionality. From the definition of key nodes to the entire process of morphological adjustment, a closed-loop design is formed through scientific multi-dimensional data processing and modeling optimization. This process reduces manual trial and error time and material waste, and provides a high-precision and directly available data model for production.

[0042] Preferably, step S24 includes the following steps:

[0043] Step S241: performing contact area recognition on the 3D printed product morphology parameter adjustment data and the human body three-dimensional model to obtain contact area recognition data; performing contact surface extraction on the 3D printed product morphology parameter adjustment data according to the contact area recognition data to obtain product-human body contact surface data;

[0044] Step S242: performing contact surface distance calculation on the product-human body contact surface data to generate product-human body contact surface distance data; performing contact surface mechanics simulation on the product-human body contact surface distance data to generate contact surface mechanics simulation data; performing fit analysis based on the contact surface mechanics simulation data to generate product fit simulation data;

[0045] Step S243: convert the product fit simulation data into a heat map to generate a product fit heat map; use the product fit heat map to three-dimensionally visualize the 3D printed product morphological parameter adjustment data to generate 3D printed product visualization data.

[0046] The present invention can accurately determine the specific area where the product contacts the human body by identifying the contact area of ​​the 3D printed product morphological parameters and the three-dimensional model of the human body. This process provides important basic data for subsequent contact surface extraction and mechanical simulation, ensuring that each contact surface in the product design can accurately reflect the surface characteristics of the human body. By extracting the contact surface data, it can be ensured that the design of the 3D printed product is completely consistent with the contact surface of the three-dimensional model of the human body, avoiding mismatches and functional failures in the design, and further improving the applicability and comfort of the product. By calculating the contact surface spacing between the product and the human body, it is possible to identify the difference in the fit of the product in different parts and provide data support for adjusting the design. Ensuring a reasonable spacing between the contact surfaces helps to reduce discomfort and avoid discomfort caused by being too tight or too loose. By analyzing the interaction between the contact surfaces through mechanical simulation, the performance of the product when actually worn, such as pressure distribution, friction, support, etc., can be evaluated. This provides a basis for the optimization of product design, ensuring that the design not only conforms to the human body morphology, but also provides comfort and stability in actual use. By performing fit analysis on the mechanical simulation data of the contact surface, the fit effect of the product can be accurately evaluated, potential design defects or mismatching areas can be discovered in time, and necessary adjustments can be made. This step is crucial to ensure the comfort of the product. This fit analysis can adjust the design in a targeted manner according to the specific morphological requirements of the human body, so as to maximize the fit effect of each part, thereby providing better personalized customization. By converting the fit simulation data into a heat map, the fit of the product to the human body contact surface can be intuitively displayed, helping designers to quickly identify problem areas. This visualization method can not only improve the efficiency of analysis, but also make adjustments more precise. Using heat maps for three-dimensional visualization can fully present the distribution of product fit. Designers can further adjust the morphological parameters of 3D printed products based on the visualization data to ensure that the final product meets the actual needs of the human body, thereby improving the comfort, adaptability and functionality of the product. Through this series of refined adjustment steps, the final 3D printed product is not only highly matched with the three-dimensional model of the human body in appearance, but also meets personalized needs in terms of function and comfort. This is especially important for personalized customized products (such as customized insoles, orthotics, sports protective gear, etc.). This process greatly reduces the time and cost waste caused by traditional manual design or multiple trial wear and debugging. Through data-driven optimization, product customization and optimization can be completed more quickly and efficiently.

[0047] Preferably, step S3 comprises the following steps:

[0048] Step S31: collecting user feedback on the 3D printing product visualization data to obtain user feedback data; extracting semantic information from the user feedback data to obtain user feedback semantic information data;

[0049] Step S32: extracting product change information from the 3D printed product visualization data according to the user feedback semantic information data to obtain product change information data; modifying the changed part parameters of the 3D printed product visualization data based on the product change information data, thereby generating a local part change model;

[0050] Step S33: Replace the local part of the local part change model and the 3D printing product visualization data, so as to generate personalized 3D printing product visualization data.

[0051] The present invention can directly obtain the user's use experience and needs by collecting user feedback on 3D printed product visualization data, ensuring that the product design can be closely connected with the actual use experience. This feedback mechanism effectively improves the pertinence and practicality of product design. Through semantic information extraction technology, key information can be extracted from user feedback, such as specific opinions on product comfort, functionality, appearance, etc., so as to provide more instructive feedback data for subsequent product optimization. This intelligent processing greatly improves the efficiency and accuracy of information processing. According to the semantic information in user feedback, the specific needs of product changes are extracted to ensure targeted improvements in certain parts of the product. This process can accurately identify the product parts that need to be adjusted, avoid irrelevant adjustments, and thus reduce unnecessary modifications and waste of resources. By modifying the parameters of the changed parts, a local part change model is generated, so that the product can be accurately adjusted according to user needs and preferences. This local change avoids large-scale redesign, improves efficiency, and can effectively meet personalized needs. The local part change model is replaced with the original 3D printed product visualization data to generate a new personalized product model. This process not only reflects a high degree of personalized customization, but also ensures seamless connection between design and user feedback, thereby improving the adaptability and user satisfaction of the final product. Through personalized adjustments, the individual needs of users can be better met, such as optimization in comfort, appearance, function, etc., to improve the overall experience and satisfaction of users. This link reflects the great advantages of 3D printing in the field of customization and promotes the interaction and co-creation between consumers and design. Through the rapid collection and intelligent processing of user feedback information, product design can be quickly iterated to reduce the cost of trial and error. This process enables the design team to obtain valuable product improvement suggestions in a relatively short period of time, greatly improving the efficiency of design adjustments. By changing the visual data, the production and testing of a large number of physical samples can be avoided, reducing costs and time, while maintaining the efficiency of personalized customization.

[0052] Preferably, step S4 comprises the following steps:

[0053] Step S41: performing printing simulation on the personalized 3D printed product visualization data to generate personalized product printing simulation data; performing effect verification on the personalized product printing simulation data to generate personalized product effect verification data;

[0054] Step S42: performing defect detection on the personalized product effect verification data to generate product printing defect detection data; performing defect location on the personalized 3D printed product visualization data using the product printing defect detection data to generate product defect location data;

[0055] Step S43: adjusting the printing material of the personalized 3D printed product visualization data according to the product defect location data, thereby generating personalized 3D printed product material adjustment data; performing virtual reality enhancement on the personalized 3D printed product visualization data based on the personalized 3D printed product material adjustment data, thereby generating a personalized 3D printed product design visualization interface to execute the 3D printed product personalized design operation.

[0056] The present invention can simulate the printing process of the product before actual printing and discover potential printing problems in advance by performing printing simulation on the personalized 3D printed product visualization data. This can not only improve the success rate of printing, but also optimize the printing strategy and printing time. The effect verification after the printing simulation ensures that the performance of the product in the actual printing meets the expectations, avoids a large number of adjustments after the actual printing, and saves time and cost. By verifying the effect in advance, the design can be optimized to ensure the quality and accuracy of the final printing result. Defect detection of the personalized product effect verification data can quickly identify defects that occur in the design or printing process of the product, such as unstable structure, rough surface, etc. This process effectively improves the printing quality and reduces the rework rate. Defect location based on defect detection data can accurately find out the weak areas and potential problems in the product, thereby providing detailed directions for subsequent design adjustments. Through accurate defect location, extensive modifications can be avoided, problems can be solved in a targeted manner, and the overall quality of the product can be further improved. According to the product defect location data, the printing material of the personalized 3D printed product visualization data is adjusted. This process helps to optimize the physical properties of the product such as strength, flexibility or durability in a specific area, ensuring that the product is fully optimized in function. Using personalized 3D printing product material adjustment data for virtual reality enhancement can provide the design team with a more intuitive and interactive visualization experience. This can not only help designers view and adjust designs in a virtual environment, but also deepen customers' understanding and recognition of product design, and enhance customer participation and satisfaction. Through printing simulation, effect verification, defect detection and material adjustment, it can ensure that the design is fully optimized in the virtual environment, thereby improving the accuracy of product design. This process avoids repeated adjustments in actual production and improves the quality of the design. Since a large amount of pre-detection and optimization is completed in the virtual environment, the actual production process can be smoother, reducing the time for debugging and correction, thereby improving production efficiency. It reduces unnecessary material waste and manual operations, and also improves the operating efficiency of the overall production line. Through printing simulation and material adjustment, the product can be further optimized according to user needs and feedback. For different user groups, it can provide tailor-made 3D printing products to meet higher personalized needs. Through printing simulation and virtual reality enhancement, the need for physical sample production is reduced, saving a lot of material and production costs. Especially in personalized customization, it can reduce development costs and improve overall production efficiency through digitalization and virtualization.

[0057] The beneficial effect of the present invention is that through the acquisition of human body three-dimensional scanning data and the analysis of movable joints, the modeling can accurately reflect the human body structure and activity characteristics, providing an accurate and dynamic human body three-dimensional model basis for subsequent design, which helps to improve the fit and comfort of the product. Body electrical impedance data acquisition and body composition calculation ensure that the model not only conforms to the human body shape, but also reflects individual physiological characteristics. Based on the personalized adjustment of these data, the design of 3D printed products is more in line with the physiological needs of users, and the personalized customization depth of the products is improved. By collecting user feedback and adjusting the local model of the product according to the feedback, the personalized needs of users can be flexibly responded to, and the design can be further refined. This method improves the customization of the product and ensures the comfort and applicability of the final product. Defect location and material adjustment in printing simulation help solve design and printing problems before production, reduce defects and waste. The virtual reality enhancement function provides a more realistic design preview, helping users to more intuitively confirm the final product effect, greatly improving the accuracy of the design and user satisfaction. Therefore, the present invention optimizes the fit and personalized design accuracy of 3D printed products by combining human joints, body composition data and user feedback, thereby improving the accuracy and flexibility of personalized design of 3D printed products. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 A schematic diagram of the steps of a personalized design method for 3D printed products based on a 3D scanned human body model;

[0059] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0060] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0061] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0062] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0063] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0064] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0065] To achieve this, please refer to Figures 1 to 3 , a 3D printing product personalized design method based on a three-dimensional scanning human body model, the method comprising the following steps:

[0066] Step S1: acquiring human body 3D scanning data and human body composition data; performing movable joint analysis on the human body 3D scanning data to generate human body movable joint data; performing distributed 3D modeling on the human body 3D scanning data based on the human body movable joint data to generate a human body 3D model;

[0067] Step S2: Based on the 3D printing technology, an initial human body fitting product design is performed on the human body three-dimensional model to obtain initial 3D printing product parameter data; the human body composition data is used to perform posture coordination analysis on the human body three-dimensional model to generate human body coordination data; the human body coordination data is imported into the initial 3D printing product parameter data to adjust the fitting morphological parameters to generate 3D printing product visualization data;

[0068] Step S3: collecting user feedback on the 3D printed product visualization data to obtain user feedback data; modifying the changed part parameters of the 3D printed product visualization data according to the user feedback data, thereby generating a local part change model; replacing the local part change model with the 3D printed product visualization data, thereby generating personalized 3D printed product visualization data;

[0069] Step S4: performing printing simulation defect location on the personalized 3D printed product visualization data to generate product defect location data; adjusting the printing material of the personalized 3D printed product visualization data according to the product defect location data to generate personalized 3D printed product material adjustment data; performing virtual reality enhancement on the personalized 3D printed product visualization data based on the personalized 3D printed product material adjustment data to generate a personalized 3D printed product design visualization interface to execute the 3D printed product personalized design operation.

[0070] The present invention enables the product to accurately adapt to the individual's body shape and range of joint motion by personalized modeling of human three-dimensional scanning data. This highly customized design improves the comfort and fit of the product and meets the user's demand for personalized products. Through the body composition analysis of electrical impedance data and the personalized three-dimensional model adjustment, the structure of the product can adapt to individual differences and ensure the best performance and support in actual use. This precise design method improves the functionality and durability of the product. Distributed modeling and automated fitting morphological parameter adjustment make the design process more efficient. Through the automatic adjustment and simulation of 3D printing product parameters, the errors of manual adjustment can be effectively avoided, and the accuracy and stability of the design can be significantly improved. Through the data processing of user feedback, the local optimization and update of the product can be quickly realized, and the change requirements proposed by the user can be met in a short time. This mechanism improves the response speed of user feedback and enhances the user's sense of participation and satisfaction. Defect location and material adjustment are carried out in the printing simulation link to avoid errors and defects in actual printing, improve the success rate and reliability of printed products, and save material and time costs. The addition of virtual reality technology provides designers and users with a more intuitive interactive experience, allowing users to fully understand and verify the design effect before printing, and further optimize the final effect of personalized products. Product design and simulation completed in a virtual environment reduces unnecessary physical sample production and resource waste, reduces design and production costs, and improves environmental protection. The automation, efficiency and accuracy of this process make the product design and manufacturing process more competitive, and can launch personalized products that meet user needs more quickly, thereby enhancing the brand's position in the customized market. Therefore, the present invention optimizes the fit and personalized design accuracy of 3D printed products by combining human joints, body composition data and user feedback, thereby improving the accuracy and flexibility of personalized design of 3D printed products.

[0071] In the embodiment of the present invention, reference Figure 1 As shown, it is a schematic diagram of the steps of a personalized design method for 3D printed products based on a three-dimensional scanning human body model of the present invention. In this example, the personalized design method for 3D printed products based on a three-dimensional scanning human body model includes the following steps:

[0072] Step S1: acquiring human body 3D scanning data and human body composition data; performing movable joint analysis on the human body 3D scanning data to generate human body movable joint data; performing distributed 3D modeling on the human body 3D scanning data based on the human body movable joint data to generate a human body 3D model;

[0073] In an embodiment of the present invention, human body surface data is collected by using a multi-angle three-dimensional scanning device (such as a laser scanner, a structured light scanner) to generate high-precision three-dimensional point cloud data. Data such as body fat percentage, muscle mass, and bone density of the human body are obtained by methods such as bioelectrical impedance analysis (BIA), dual-energy X-ray absorptiometry (DXA), or magnetic resonance imaging (MRI). Skeleton information is extracted from the three-dimensional scanning point cloud data of the human body to identify the main joints of the human body (such as shoulders, elbows, knees, hips, etc.). Based on the skeleton model, the range of motion of the joints (such as bending angles and rotation angles) is analyzed by geometric calculations or motion capture equipment. Combined with the range of motion, the three-dimensional coordinates, activity angles, and constraints of each joint are generated to form the data of movable joints of the human body. According to the data of movable joints of the human body, the three-dimensional scanning point cloud is divided into multiple regions (such as upper arms, lower arms, thighs, and calves). Using a distributed computing framework (such as Hadoop and Spark), the data of each region is modeled in parallel to generate a local three-dimensional model. The local three-dimensional models are spliced ​​by joint coordinates and activity angles to generate a three-dimensional model of the whole human body. Map human body composition data to a 3D human model, such as by color coding to show fat distribution or muscle density. Use surface reconstruction algorithms (such as Poisson reconstruction, Marching Cubes) to refine the model and generate a realistic surface structure. Dynamically adjust the joint area of ​​the model based on the data of the movable joints of the human body to ensure that the reconstructed model has the ability to move naturally at the joints. Integrate the results of the above steps to output a complete 3D human model that contains both the human body geometry and the body composition data, which can be used for applications such as motion analysis, medical diagnosis, or virtual reality.

[0074] Step S2: Based on the 3D printing technology, an initial human body fitting product design is performed on the human body three-dimensional model to obtain initial 3D printing product parameter data; the human body composition data is used to perform posture coordination analysis on the human body three-dimensional model to generate human body coordination data; the human body coordination data is imported into the initial 3D printing product parameter data to adjust the fitting morphological parameters to generate 3D printing product visualization data;

[0075] In an embodiment of the present invention, the human body three-dimensional model generated in step S1 is imported into 3D design software (such as Fusion360, SolidWorks). According to the purpose of the product (such as protective gear, prosthesis or wearable device), the preliminary product structure and form are set. The curvature information of the human body surface is extracted by using a model surface fitting algorithm (such as NURBS or B-spline surface) to generate a fitting surface. A buffer layer or a support structure is added to key areas (such as joints and pressure points) to improve comfort and adaptability. Design parameters (such as size, thickness, and radius of curvature) are extracted to form initial 3D printed product parameter data. The posture of the human body in static and dynamic conditions is analyzed by a human motion capture system (such as Kinect, Vicon) or a posture-based simulation algorithm. The left-right symmetry of the shoulders, hips and other parts is evaluated. The natural curvature of the spine and limbs (such as hunchback and scoliosis) is evaluated. The center of gravity offset of the human body when standing or walking is analyzed by mass center calculation. The above analysis results are converted into human body coordination data, including posture adjustment suggestions and related parameters (such as bending angle deviation and symmetry coefficient). Take the human body coordination data as input to adjust the initial 3D printing product parameter data. Fine-tune the fitting surface according to the body coordination data (such as correcting the support structure in the spine area). Use finite element analysis (FEA) to simulate the pressure distribution of the product during use and optimize the thickness and material distribution in key areas. Flexibly optimize the morphological design of the product in the joint or bending area to ensure that it does not affect the movement function. Generate 3D printing product visualization data through 3D design software, including the geometry of the model, the material and color to be printed, etc. Display the final model in the form of high-precision three-dimensional graphics to verify whether the design fits the human body reconstruction model and coordinates the body posture. Convert the model to a format supported by the 3D printer (such as STL, OBJ) with material parameters (such as elastic coefficient, layer height).

[0076] Step S3: collecting user feedback on the 3D printed product visualization data to obtain user feedback data; modifying the changed part parameters of the 3D printed product visualization data according to the user feedback data, thereby generating a local part change model; replacing the local part change model with the 3D printed product visualization data, thereby generating personalized 3D printed product visualization data;

[0077] In an embodiment of the present invention, a feedback collection system is built to allow users to experience the initial 3D printed product model through online or physical testing. Users can submit feedback in the form of voice, text or rating, especially opinions on fit, comfort and functionality. The collected user feedback data is sorted and analyzed to extract key opinions on each part, including which parts need to be improved or adjusted. Finally, user feedback opinion data is generated to provide a basis for the next step of change. The user feedback opinion data is semantically analyzed to convert the parts involved in the adjustment and specific modification suggestions into operational design requirements, such as increasing elasticity, reducing thickness or increasing support force. According to the extracted design requirements, the local part parameters that need to be adjusted in the 3D printed product visualization data are modified, including adjusting parameters such as size, curvature or material distribution. After the parameter adjustment is completed, the changed part generates a local part change model, which has the personalized features specified by the user and can better meet the actual needs of the user. A local replacement algorithm is designed to merge the modified part of the local part change model with the original 3D printed product model. Ensure seamless connection during the replacement process without excessive stretching or shrinkage. The adjusted local model is integrated with the overall 3D printed product visualization data to generate personalized 3D printed product visualization data. This model not only meets the needs of user feedback, but also retains the integrity of the original design. The generated personalized 3D printed product visualization data can be directly used for display, simulation or further printing to ensure that the comfort and functionality of the product in actual use meet the standards.

[0078] Step S4: performing printing simulation defect location on the personalized 3D printed product visualization data to generate product defect location data; adjusting the printing material of the personalized 3D printed product visualization data according to the product defect location data to generate personalized 3D printed product material adjustment data; performing virtual reality enhancement on the personalized 3D printed product visualization data based on the personalized 3D printed product material adjustment data to generate a personalized 3D printed product design visualization interface to execute the 3D printed product personalized design operation.

[0079] In an embodiment of the present invention, by importing personalized 3D printed product visualization data into simulation software, a simulation model is established based on the geometric structure, material and expected load conditions of the product to simulate possible problems in the printing process. During the simulation process, defects (such as warping, shrinkage, poor interlayer bonding, etc.) are monitored layer by layer. Finite element analysis and other methods are used to identify existing structural defects. The location, type and severity of the defects detected in the simulation are recorded to generate product defect location data for targeted adjustments in subsequent steps. Based on the defect location data, a material adjustment strategy is formulated. For example, the material density is increased in areas with greater structural stress, or a more elastic material is selected in areas where flexibility is required to reduce the probability of defects. Through layered material allocation or local material replacement, the optimized material properties are applied to the product model to ensure that the mechanical properties and printing effects of key areas meet expectations. All material adjustment results are summarized to generate personalized 3D printed product material adjustment data to ensure that the material parameters of each part meet the design requirements and can be used in the printing stage. Import the material-adjusted personalized 3D printing product data into the virtual reality (VR) system, and simulate the interactive experience and visual feedback in the real environment to allow users to "try out" the product in a virtual environment to feel its fit, functionality, and comfort. Create a three-dimensional visualization interface to display the product's appearance, material characteristics, and key design details through the VR interface, allowing users to rotate, zoom, and zoom in to gain a deeper understanding of the effect of personalized design. The generated personalized 3D printing product design visualization interface can be used for display and review, helping the design team to confirm whether it meets user expectations and provide the final design basis and visualization support for personalized 3D printing product design operations.

[0080] Preferably, step S1 comprises the following steps:

[0081] Step S11: obtaining three-dimensional scanning data of a human body; obtaining human body composition data using a body composition calculation formula;

[0082] Step S12: performing data preprocessing on the human body three-dimensional scanning data to generate standard human body three-dimensional scanning data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization;

[0083] Step S13: performing movable joint analysis on the standard human body three-dimensional scanning data to generate human body movable joint data; performing human body part division on the standard human body three-dimensional scanning data based on the human body movable joint data to generate human body part division data;

[0084] Step S14: Perform distributed 3D modeling on the standard human body 3D scanning data using the human body part division data to generate a human body 3D model; perform 3D reconstruction on the human body 3D model using the human body composition data to generate a human body 3D model.

[0085] In an embodiment of the present invention, a human body is scanned by using a high-precision three-dimensional scanning instrument (such as a laser scanner or a structured light scanner) to obtain fine three-dimensional data of the human body. During the scanning process, it is necessary to ensure that the scanned data obtained covers all parts of the human body, especially the joints, limbs and torso, to ensure the integrity and accuracy of the data. Inaccurate data points caused by noise or occlusion during the scanning process are removed, and valid three-dimensional point cloud data is retained. Filtering techniques (such as Gaussian filtering, mean filtering, etc.) are applied to remove random noise in the scanned data to ensure data smoothness. Interpolation algorithms (such as nearest neighbor interpolation and Laplace interpolation) are used to fill in the data missing areas caused by scanning angle limitation or occlusion. The data is normalized to the coordinate system, and the three-dimensional data is unified into the standard coordinate system to ensure the consistency of all scanned data, which is convenient for subsequent analysis and processing. The body composition calculation formula is used to obtain the body composition data of the human body, and the main joints of the human body (such as shoulder joints, elbow joints, knee joints, etc.) are identified by analyzing the joint areas in the standard three-dimensional scan data of the human body. Machine learning or rule-based algorithms (such as bone recognition algorithms) are used to identify joint positions and ranges of motion, and to generate motion restriction data and range of motion information for each movable joint of the human body. The 3D scan data of the human body is segmented into several regions using joint data, usually according to different parts of the limbs (such as the head, trunk, limbs, etc.). The boundary of each part can be ensured to be accurate and reasonable by combining joint-based geometric segmentation methods with automated algorithms, such as surface-based segmentation algorithms. Based on the data of each human body part that has been segmented, a 3D model of each part of the human body is constructed using 3D modeling technology (such as voxel modeling and surface reconstruction). Then, a distributed computing platform is used to integrate and optimize the 3D data of each part to generate a complete high-precision 3D model of the human body. This model will contain detailed joint ranges of motion and geometric features of each part, and can be used for subsequent virtual human analysis, motion simulation, or medical research applications. Import human body composition data, including fat distribution, muscle density, bone density, etc. By matching the body composition data with the spatial coordinates of the 3D model, each body composition data point is mapped to the corresponding area of ​​the 3D model. For missing or sparse areas, use three-dimensional interpolation algorithms (such as Kriging interpolation and IDW interpolation) to complete the data and ensure the continuity of body composition information on the model. Reconstruct the model using body composition data: adjust the local thickness of the model surface according to the fat distribution data. Generate surface textures of different material areas through muscle density data to reflect the distribution characteristics of muscle and fat. Combined with the data of movable joints of the human body, dynamically adjust the morphology of the active area of ​​the reconstructed model to make it show natural transitions and bends at the joints. Globally optimize the reconstructed three-dimensional model, use surface smoothing algorithms to remove redundant details, and improve visual and physical simulation effects. Output a complete three-dimensional human body model with both geometric accuracy and physiological information, suitable for personalized custom design or medical research.

[0086] Preferably, the formula for calculating body composition in step S11 is as follows:

[0087]

[0088] In the formula, Expressed as lean body mass, Expressed as the maximum measurement frequency, Expressed as the impedance weighting coefficient, Represents the human body at frequency The impedance value below Expressed as the height weighting coefficient, is the height of the individual, Expressed as the weight-frequency weighting coefficient, is the weight of the individual, Expressed as the age weighted coefficient, is represented as an exponential decay term of age, is the individual age, Expressed as an exponent. Expressed as the age exponential decay coefficient.

[0089] The present invention analyzes and integrates a body composition calculation formula. The principle of the formula is that different tissues in the human body (such as fat, muscle, water, etc.) have different electrical conductivities, so the body composition can be inferred by measuring electrical impedance. For example, tissues with high water content (such as muscle) have lower electrical impedance, while fat tissue has higher electrical impedance due to its low water content. Through multi-frequency measurement, the penetration depth and response characteristics of currents of different frequencies make the electrical impedance data more comprehensive. Combined with individual information such as height, weight, and age, the formula balances multiple weighted items and accumulates integrals to produce a more reliable estimate of lean body mass. At the frequency The measured electrical impedance It reflects the distribution of water and highly conductive tissues such as muscles in the body. Weighted, significantly affecting the contribution of water and muscle to lean body mass. The weighting of water and muscle content is significant, the formula is more sensitive to highly conductive tissues, and the resulting lean body mass estimate is more accurate, especially for individuals with a greater influence of water content (such as athletes). Height squared term Simulates the size of the body surface area and adjusts the impedance results based on the surface area. A larger body surface area generally means a higher overall mass. Adjusting the calculation of lean body mass based on body surface area enhances the formula's adaptability to individuals of different heights, allowing it to maintain accuracy in a variety of body types. With measurement frequency The logarithmic relationship of reflects the influence of body weight on the overall conductivity and frequency response. The importance of this control. The logarithmic frequency term helps to smooth the response variation at different frequencies, reduce the influence of frequency extremes, and make the body composition estimate more robust to different frequencies. It is particularly useful for deriving balanced body composition results from multi-frequency data. The exponential decay term describes the natural decay effect of age on body composition (especially lean body mass), which is expressed by and Control its intensity. The older the age, the more significant this attenuation is. The nonlinear attenuation of age takes into account the natural trend of muscle and water content decreasing with age. In this way, the formula maintains accuracy at all ages and effectively avoids errors caused by ignoring the age factor. When using the conventional body composition calculation formula in the field, the fat-free body mass can be obtained. By applying the body composition calculation formula provided by the present invention, the fat-free body mass can be calculated more accurately. The formula integrates impedance data of different frequencies through integral operations, effectively utilizing the characteristics of low frequency penetrating the fat layer and high frequency penetrating cells, making the formula more in-depth and broad when estimating body composition. By weighted control of individual height, weight, and age, the formula is more adaptable to different body shapes and age groups, and the estimated results are more in line with the actual physiological state. Multiple weighted parameter controls enable the formula to accurately adjust the weights of each influencing factor. Compared with simple formulas, this complex formula shows higher accuracy in a wider range of people.

[0090] Preferably, the distributed 3D modeling of the standard human body 3D scan data by using the human body part division data comprises the following steps:

[0091] Calculating the area of ​​the human body part division data to obtain the area data; performing regional segmentation on the standard human body three-dimensional scanning data based on the area data to generate human body part regional segmentation data, wherein the human body part segmentation data includes main part regional segmentation data and secondary part regional segmentation data;

[0092] Assigning a high modeling priority to the main part region segmentation data and a low modeling priority to the secondary part region segmentation data, thereby obtaining part region modeling priority data, and performing distributed computing node allocation on the human body part region segmentation data according to the part region modeling priority data, thereby generating distributed region modeling data;

[0093] Perform local modeling on the distributed regional modeling data to generate a local three-dimensional model of the human body part; confirm the part connection points of the local three-dimensional model of the human body part to obtain the part connection center point data; and splice the local three-dimensional model of the human body part according to the part connection center point data to generate a three-dimensional model of the human body.

[0094] In an embodiment of the present invention, complete human body data, including point cloud data and geometric structure data, is obtained from a high-precision human body three-dimensional scanning system (such as LiDAR or optical scanning). The three-dimensional human body data is preliminarily divided based on anatomical standards or using an automated algorithm (such as a deep learning model). Common parts include the head, torso, limbs, fingers, toes, etc. After the division, the human body is marked as a main part (such as torso, limbs) and a secondary part (such as fingers, toes). The point cloud surface is fitted for each part area, and the surface area of ​​each part is calculated using a volume calculation formula (such as based on polygon segmentation or volume voxel method). According to the three-dimensional geometric information of the scanned data, the surface area data of each part is calculated. According to the characteristics of the part area size, shape, etc., the standard human body three-dimensional scanned data is segmented to determine the boundary between the main part and the secondary part. The scanned data is divided into the main part area segmentation data and the secondary part area segmentation data. High modeling priority is given to important or large-area parts (such as torso, limbs). Low modeling priority is given to small or non-major structure parts (such as fingers, toes). According to the area and functional requirements of the parts (such as criticality, stability requirements, etc.), a weight value is assigned to each area to generate the priority data for part area modeling. According to the priority data, the main parts are assigned to nodes with strong computing power for high priority modeling, and the secondary parts are assigned to low priority nodes for processing. Load balancing algorithms (such as Round Robin, weighted polling) or priority-based allocation algorithms are used to parallel process the part area data on distributed computing platforms (such as Hadoop, Spark) to generate distributed area modeling data. Point cloud processing and surface reconstruction technology, such as Poisson Surface Reconstruction or Marching Cubes algorithm, are used to generate a local 3D model of each part. Smoothing algorithms (such as Laplacian smoothing) are used to remove noise, optimize the accuracy and details of the local 3D model, and ensure that the morphology of each part conforms to the real structure of the human body. Between each local 3D model, the connection points of each part are identified through geometric distance calculation and topological analysis methods. These connection points are the key nodes for transition and connection between human body parts. Based on the geometric calculation and topological structure of the connection points, the connection center point data of each part is generated, including the connection order and local characteristics between parts. According to the data of the connected center points, the iterative closest point (ICP) algorithm or the least squares method is used to stitch the model together to ensure that the local models are accurately stitched together to generate a complete human body 3D model. The stitched model is further adjusted using a global optimization algorithm (such as nonlinear least squares optimization) to eliminate errors in the stitching process and ensure that the 3D model is smooth and natural. After the local model is stitched together, smoothing (such as B-spline or Laplacian smoothing) is used to eliminate mutations in the seam area to ensure that the model surface is smooth and has no obvious stitching marks.By comparing the human body 3D model with standard human body 3D scanning data, the geometric accuracy of the model is verified to ensure that the model conforms to the actual human body structure.

[0095] Preferably, confirming the connection points of the local three-dimensional model of the human body part includes:

[0096] Extracting the part boundary point set from the local three-dimensional model of the human body part to obtain the part boundary point set; performing boundary detection on the part boundary point set to generate potential connection point data of the part boundary;

[0097] The distance between the boundary points of adjacent parts of the local three-dimensional model of the human body parts is calculated by using the potential connection point data of the boundary of the parts to obtain the distance data of the boundary points of adjacent parts; the distance data of the boundary points of adjacent parts is compared with the preset standard boundary point distance threshold, and when the distance data of the boundary points of adjacent parts is less than or equal to the preset standard boundary point distance threshold, the overlapping boundary point area is screened based on the distance data of the boundary points of adjacent parts to obtain the overlapping boundary point area data of adjacent parts;

[0098] The data of the overlapping boundary points of adjacent parts are distributed with part connection points to generate the spatial distribution data of the part connection points; the coordinates of the center points of the connected areas of the overlapping boundary points of adjacent parts are calculated through the spatial distribution data of the part connection points to generate the data of the part connection center points.

[0099] In an embodiment of the present invention, the boundary points of each part are identified and extracted by using three-dimensional scanning data. The boundary point set of each part of the human body is extracted by point cloud data processing technology (such as a curvature-based boundary detection method or normal vector analysis). These points are usually located at the edge of the part and can help locate the boundary area between different parts. By removing noise points and redundant points, it is ensured that the extracted boundary point set only contains valid points representing boundary features. The extracted boundary point set is analyzed by a boundary detection algorithm (such as a gradient-based edge detection method or a clustering method based on boundary feature points) to identify potential connection points between parts. Potential connection points are usually points at the junction of parts or joint areas, and these points have a high probability of becoming actual connection points. According to the boundary detection results, potential connection point data of the part boundary is generated, that is, all connected points found in the boundary detection process. Based on the potential connection point data of the part boundary, the boundary point distance between adjacent parts is calculated. This can be achieved by calculating the Euclidean distance or an algorithm based on distance transformation. For example, a nearest neighbor algorithm can be used to find the nearest point pair between the boundary point sets of two parts and calculate the distance between them. The calculated distance is stored as the distance data of the boundary points of adjacent parts, which can help identify the proximity of the boundary points and provide a basis for subsequent boundary screening. The calculated distance between the boundary points of adjacent parts is compared with the preset standard boundary point distance threshold. The standard threshold is set by experiments or knowledge of human anatomy, and usually corresponds to the critical distance of the boundary contact of adjacent parts. When the distance of some boundary point pairs is less than or equal to the threshold, this part of the area is considered to be the contact area of ​​the adjacent parts, so it is classified as the overlapping boundary point area. These overlapping areas indicate the connection points between adjacent parts. Based on the screening conditions, the data of the overlapping boundary point areas of adjacent parts are generated, which is the basis for further confirming the connection points of the parts. Based on the data of the overlapping boundary point areas of adjacent parts, spatial distribution analysis is performed to determine the location of the connection points of the parts in the overlapping area. This can be calculated by statistical methods or algorithms based on shape matching for spatial distribution. By calculating the point set in each overlapping area, the spatial distribution data of the connection points of the parts are generated, and the specific location of the connection points in three-dimensional space is recorded to provide a reference for subsequent model splicing. Using the spatial distribution data of the part connection points, cluster or calculate the centroid of the connection points in each overlapping area to determine the center point of each connected area. This can be done by using a weighted average method or using a K-means clustering algorithm to determine the coordinates of the center point of each area. Generate part connection center point data, that is, the coordinates of the connection center points of adjacent parts in three-dimensional space. This center point marks the connection area between parts and provides accurate connection information for subsequent model splicing and optimization.

[0100] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0101] Step S21: performing an initial human body fitting product design on the human body three-dimensional model based on 3D printing technology to obtain initial 3D printing product parameter data;

[0102] Step S22: using the human body composition data to perform posture coordination analysis on the human body three-dimensional model to generate human body posture coordination data; extracting part morphological features of the human body three-dimensional model according to the human body posture coordination data to obtain part morphological feature data;

[0103] Step S23: adjusting the product morphology parameters of the initial 3D printing product parameter data according to the part morphology feature data to generate 3D printing product morphology parameter adjustment data;

[0104] Step S24: simulating the product fit of the human body three-dimensional model through the 3D printing product morphological parameter adjustment data, thereby generating product fit simulation data; and three-dimensionally visualizing the 3D printing product morphological parameter adjustment data based on the product fit simulation data, thereby generating 3D printing product visualization data.

[0105] In an embodiment of the present invention, the complete human body three-dimensional model obtained from the previous step (such as by scanning or three-dimensional reconstruction) is used for subsequent product design. The preliminary fitting product is designed based on the human body three-dimensional model, with the goal of providing a comfortable fitting structure that conforms to the biomechanical characteristics of the human body, such as a customized prosthesis, sports protective gear or fitted clothing. The human body three-dimensional model is analyzed using CAD (computer-aided design) tools or specialized 3D modeling software (such as SolidWorks, Rhinoceros) to generate an initial design model of the product (such as an insole, a bracket, an armor protective gear, etc.). According to the product design requirements (size, shape, material, etc.), preliminary 3D printing product parameter data is generated, such as product size, shape, pore structure, surface smoothness, etc. By analyzing the natural posture, movement pattern and anatomical characteristics of the human body, the coordination of the human body in different postures is identified, so as to design products that can support or improve the human body posture. Computer vision and machine learning algorithms (such as posture estimation algorithms, motion capture technology) are used to perform dynamic posture analysis of the human body to generate data reflecting the coordination of the human body in a specific posture (for example, joint angles, muscle stress distribution, motion trajectory, etc.). Based on the human body coordination analysis data, the morphological feature data of different parts of the human body (such as waist, shoulder, knee, etc.) are extracted, including but not limited to curves, joint angles, curvature, surface convexity, etc. Morphological analysis algorithms (such as edge detection, surface fitting, point cloud analysis) are used to identify the geometric features of each human body part and quantify its morphological feature data. The initial 3D printing product parameters are adjusted using morphological algorithms to ensure that it can fit the human body to the greatest extent on the basis of conforming to the human body morphological characteristics. By adjusting the product surface, curve, thickness and other parameters, the 3D printing product can better adapt to the morphological characteristics of the human body parts, such as optimizing the flexibility of the joint parts and reinforcing the areas that need to bear greater pressure. Optimization algorithms (such as genetic algorithms and simulated annealing algorithms) are used to optimize the parameters of the 3D printing product according to the part morphological feature data to generate adjusted product parameter data. Finally, a set of 3D printing product parameter data after morphological adjustment is output, including information such as size, structure, and material distribution. Use finite element analysis (FEA) or physical simulation software (such as ANSYS, COMSOL) to simulate the product fit, simulating the deformation, compression and force of the product when it contacts the human body. Based on the simulation results, generate product fit data, covering information such as contact area, pressure distribution, and degree of deformation. These data can help evaluate the fit between the product and the human body and ensure the rationality of product design. By using visualization software (such as Blender, Unity3D), the morphological parameter adjustment data of 3D printed products is visualized in three dimensions to show the fit effect of the adjusted product on the human body. Through dynamic demonstrations or interactive models, show the details of the product's contact with the human body, such as how to adapt to the human body curve, how to enhance comfort or support.Through the combination of virtual human body and 3D printed products, the adaptability of the product in different body shapes can be further verified and finally optimized.

[0106] Preferably, importing the human body composition data into the human body three-dimensional model to adjust the personalized three-dimensional model includes:

[0107] Defining key nodes of the body contour of the three-dimensional human body model and generating key node data of the body contour; dividing the model surface mesh of the three-dimensional human body model based on the key node data of the body contour and generating model surface mesh data;

[0108] Importing the body part morphological feature data into the human body three-dimensional model for body composition data mapping to generate body composition mapping data; using the body composition mapping data to perform body composition region association on the model surface mesh data to generate body composition region association data;

[0109] Performing mesh surface deformation analysis on the body component region association data to generate mesh surface deformation data; performing mesh node adjustment on the body component region association data according to the mesh surface deformation data to generate mesh part contour node adjustment data;

[0110] The printing level in the initial 3D printing product parameter data is adjusted through the mesh part contour node adjustment data to generate 3D printing product morphological parameter adjustment data, wherein the printing level adjustment includes muscle layer adjustment and skin layer adjustment.

[0111] In an embodiment of the present invention, key contour nodes are defined at different parts of the human body three-dimensional model (such as shoulders, chest, abdomen, buttocks, limbs, etc.) for subsequent adjustment and optimization. The key contour points of the human body three-dimensional model are automatically identified by using morphological analysis algorithms, surface fitting, and feature extraction technology of three-dimensional scanning data (such as edge detection algorithms). The key node data of the part contour is output, including the spatial coordinates (X, Y, Z) of each key node and the boundary information of each part of the human body. The surface of the human body three-dimensional model is meshed to make detailed adjustments and optimizations to each mesh unit. According to the key node data of the part contour, the surface of the model is meshed using a meshing algorithm (such as Delaunay triangulation, tetrahedral meshing) to ensure that the mesh can accurately cover all details of the human body surface. The model surface mesh data is output, including the coordinates of the mesh nodes and the topological structure of each mesh unit. The human body composition data (such as distribution data of fat, muscle, bone, etc.) is mapped to the human body three-dimensional model for personalized adjustment. Using the spatial relationship between body composition data and the human body 3D model, the body composition information is mapped to each grid unit of the model through data fusion algorithms (such as weighted average method, interpolation method, etc.). Output body composition mapping data, including information such as fat content, muscle density, and bone volume in each grid unit. According to the body composition data, different areas of the human body 3D model are associated with the body composition data to ensure that personalized adjustments are consistent with the actual physiological structure. Use clustering algorithms (such as K-means algorithm, density clustering) to analyze the body composition mapping data and divide the surface of the human body model into different body composition areas. For example, it can be divided into high muscle areas, low fat areas, etc. according to regional characteristics such as fat and muscle. Output body composition area association data, including the name, range, and body composition characteristics of each area (such as muscle density, fat layer thickness, etc.). Analyze the mesh deformation of the surface of the human body 3D model to ensure that it is closely matched with the relationship between the body composition area, so as to make personalized adjustments. Perform mesh surface deformation analysis on the body composition area association data through finite element analysis (FEA) or physical simulation technology. This analysis will simulate the effects of different body composition regions (such as muscle, fat, etc.) on the surface morphology of the model, such as muscle expansion, fat compression, etc. Output mesh surface deformation data, including the deformation amount, deformation direction, force analysis results, etc. of each mesh unit. According to the mesh surface deformation data, the mesh nodes are adjusted to achieve a more accurate personalized three-dimensional model. Use shape optimization algorithms (such as gradient descent method and minimum energy method) to adjust the mesh nodes and modify the mesh surface according to the deformation of the body composition region to ensure the true fit of the product. Output mesh part contour node adjustment data, indicating the new coordinates and morphological characteristics of each mesh node. According to the adjusted mesh node data, the hierarchical structure of the 3D printed product is further optimized, especially in the design of the muscle layer and skin layer, to meet the needs of different body composition regions.Using the adjusted mesh part contour node data, adjust the thickness, density and other parameters of the muscle layer and skin layer respectively. For example, the layer thickness of the muscle area may need to be increased to accommodate the volume and force distribution of the muscle, while the skin area may require a thinner design. Output the 3D printing product morphological parameter adjustment data, covering the thickness, density, texture and other adjustment parameters of the muscle layer and skin layer. Based on the adjusted product morphological parameters (including printing level, density, morphological adjustment, etc.), generate 3D printing files that conform to human body characteristics, such as STL files, OBJ files, etc.

[0112] Preferably, step S24 includes the following steps:

[0113] Step S241: performing contact area recognition on the 3D printed product morphology parameter adjustment data and the human body three-dimensional model to obtain contact area recognition data; performing contact surface extraction on the 3D printed product morphology parameter adjustment data according to the contact area recognition data to obtain product-human body contact surface data;

[0114] Step S242: performing contact surface distance calculation on the product-human body contact surface data to generate product-human body contact surface distance data; performing contact surface mechanics simulation on the product-human body contact surface distance data to generate contact surface mechanics simulation data; performing fit analysis based on the contact surface mechanics simulation data to generate product fit simulation data;

[0115] Step S243: convert the product fit simulation data into a heat map to generate a product fit heat map; use the product fit heat map to three-dimensionally visualize the 3D printed product morphological parameter adjustment data to generate 3D printed product visualization data.

[0116] In an embodiment of the present invention, the 3D printed product morphology parameter adjustment data and the human body three-dimensional model are interacted by using a collision detection algorithm (such as an algorithm based on volume collision or an algorithm based on surface collision) to identify the contact area between the product and the human body. The process obtains contact area identification data by identifying the contact points between the model surfaces, which includes information such as the boundary, shape, and area of ​​the contact area. The identification of the contact area can use acceleration algorithms such as the AABB (axis-aligned bounding box) algorithm and the KD tree algorithm to improve the calculation efficiency. Based on the contact area identification data, the 3D printed product morphology parameter adjustment data and the human body three-dimensional model are further processed to extract the contact surface. By selecting the surface mesh in the contact area, the geometric properties of each mesh unit on the contact surface (such as normal vector, area, curvature, etc.) are obtained to obtain the product-human body contact surface data. This process uses the gridded modeling information to identify which mesh areas are in contact between the product and the human body, and analyzes its surface features (such as curvature, concave and convex, etc.). The contact surface spacing of the product-human body contact surface data is calculated. The calculation process includes calculating the minimum distance between each contact point on the product and the human body surface. This can be achieved through geometric distance calculation methods, such as calculating the distance from a point to a surface, or using distance field methods for efficient processing. Generate product-body contact surface spacing data, which contains the distance value of each contact surface point. The distribution of spacing will be used for subsequent fit analysis. Use finite element analysis (FEA) or contact mechanics simulation technology to simulate the product-body contact surface spacing data. This step takes into account the contact force, pressure distribution and surface deformation between the product and the human body surface. In particular, for flexible products, simulate the mechanical response (such as compression, bending, etc.) on the contact surface. Using the contact mechanics model, combined with the stiffness of the human body surface, the elastic modulus of the product material and other properties, the contact surface is mechanically analyzed to generate contact surface mechanical simulation data. This data includes force distribution on the contact surface, pressure concentration area, force direction, etc. Based on the contact surface mechanical simulation data, further fit analysis is performed. The goal of the analysis is to evaluate the fit between the product and the human body surface and determine whether there is uneven contact pressure or poor fit area. By analyzing the mechanical response of the contact area, we can identify which areas have excessive pressure (such as areas with strong pressure) and which areas are loose (such as areas without sufficient contact force). Generate product fit simulation data, which includes evaluation of the fit area (such as tightness, pressure uniformity, etc.). Convert the product fit simulation data into a heat map, which can be done through a heat map visualization tool (such as using visualization software such as Matplotlib or Paraview). In the heat map, different colors are used to represent the fit of the contact area. For example, green represents the best fit area, red represents areas with excessive pressure or poor fit, and blue represents areas with no contact.This heat map can clearly show which areas have a good fit and which areas need improvement, so that designers can make optimization adjustments. Use 3D visualization technology (such as OpenGL, Unity3D, etc.) to visualize the product fit heat map in three dimensions. This process will visualize the contact area and fit distribution between the product and the human body in a 3D model. Overlay the fit heat map on the model, highlight the poor contact areas through color mapping and highlight effects, and help designers better understand and optimize the design. The generated 3D printed product visualization data will provide an important basis for subsequent product design, adjustment, and 3D printing process.

[0117] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0118] Step S31: collecting user feedback on the 3D printing product visualization data to obtain user feedback data; extracting semantic information from the user feedback data to obtain user feedback semantic information data;

[0119] Step S32: extracting product change information from the 3D printed product visualization data according to the user feedback semantic information data to obtain product change information data; modifying the changed part parameters of the 3D printed product visualization data based on the product change information data, thereby generating a local part change model;

[0120] Step S33: Replace the local part of the local part change model and the 3D printing product visualization data, so as to generate personalized 3D printing product visualization data.

[0121] In an embodiment of the present invention, user feedback is collected by using an online feedback platform (such as a questionnaire, a feedback form) or a user test (such as a virtual reality display). These feedbacks can be collected through an automated system or a manual survey. The collected user feedback content may include information such as user perception of product design, user experience, comfort, functional evaluation, etc. Data collection tools include user rating systems, voice input interfaces (such as voice recognition technology), text input boxes, etc. to obtain multi-dimensional user feedback. All user feedback is summarized and sorted to obtain user feedback data, which will contain comments, suggestions, and evaluations of multiple users. The user feedback data is semantically analyzed, and the key information is extracted using natural language processing (NLP) technology. Commonly used techniques include word segmentation, part-of-speech tagging, sentiment analysis, topic modeling, etc. For example, the user's positive or negative emotions towards a specific design are judged by sentiment analysis, and the core issues that the user is concerned about (such as "uncomfortable touch" and "need more space" are found out through keyword extraction. Combined with machine learning algorithms (such as classification models or deep learning models based on support vector machines (SVMs)), the feedback text is processed and converted into a structured data form to obtain user feedback semantic information data, which contains specific modification suggestions or requirements for the design, such as color adjustment, morphological changes, etc. Based on the user feedback semantic information data, product change information is extracted from it, which includes product details or design directions that users want to adjust (for example, changing the shape of a certain part, adjusting product size or material, etc.). The semantic information of user feedback is inferred and analyzed through a rule engine or a deep learning model to automatically generate product change information data. These data specifically describe which parts need to be changed, the direction or range of the change, for example, "increasing the width of the shoulder", "changing the bending angle of the wrist", etc. Using a model optimization algorithm, combined with feedback information, the deficiencies and potential improvement points in the product design are identified, and corresponding change suggestions are generated. Based on the product change information data, the original 3D printed product visualization data is modified. The modifications include: Local shape adjustment: For example, adjusting the morphology of the part through surface reconstruction or mesh editing technology. Size adjustment: Based on user feedback, a size adjustment algorithm is used to expand or shrink certain areas. Detail optimization: For example, adding or reducing local details (such as the grip area of ​​the handle, the foot support surface, etc.). According to the change requirements, the geometric parameters of the 3D model are locally adjusted to generate a local part change model, which only optimizes the parts involved in user feedback and does not affect the design of other parts. Edit the local parts through CAD tools or modeling software (such as SolidWorks, Blender) to ensure that the adjusted parts are smoothly connected to the original design to avoid inharmonious structures. After obtaining the local part change model, combine it with the original 3D printed product visualization data through the model fusion algorithm.This process involves seamlessly connecting the changed local parts with the original model to ensure that the changed parts are perfectly integrated with other parts to avoid mismatches or geometric discontinuities. After completing the local replacement, the integrated model is smoothed, the seams are optimized, and the edge defects of the seams are removed using mesh reconstruction technology to ensure that it meets the requirements of 3D printing. The final personalized adjustment results are presented to the user in a 3D visualization form, and the final personalized 3D printed product visualization data is generated, which has all the optimizations and adjustments made based on user feedback, providing a complete visualization effect.

[0122] Preferably, step S4 comprises the following steps:

[0123] Step S41: performing printing simulation on the personalized 3D printed product visualization data to generate personalized product printing simulation data; performing effect verification on the personalized product printing simulation data to generate personalized product effect verification data;

[0124] Step S42: performing defect detection on the personalized product effect verification data to generate product printing defect detection data; performing defect location on the personalized 3D printed product visualization data using the product printing defect detection data to generate product defect location data;

[0125] Step S43: adjusting the printing material of the personalized 3D printed product visualization data according to the product defect location data, thereby generating personalized 3D printed product material adjustment data; performing virtual reality enhancement on the personalized 3D printed product visualization data based on the personalized 3D printed product material adjustment data, thereby generating a personalized 3D printed product design visualization interface to execute the 3D printed product personalized design operation.

[0126] In an embodiment of the present invention, the visualization data (i.e., the complete 3D model) of the personalized 3D printed product is imported into the printing simulation software (such as Simplify3D, PrusaSlicer, Cura, etc.). These simulation tools can simulate the layer-by-layer stacking, support structure generation, and printing path planning during the printing process. The simulation tool will simulate the problems that occur during the actual printing process, such as the deposition of materials, the stability of the support structure, etc. The software will generate detailed simulation data of the printing process, including parameters such as the printing path, interlayer connection, material usage, and printing speed. This data not only shows the details of the printing process, but also can discover potential problems in advance, such as the area where printing failed, printing errors, etc. The accuracy of the simulation results affects the subsequent steps, so the appropriate simulation accuracy should be selected to ensure that the performance in the actual printing can be accurately predicted. After the simulation is completed, the performance of the printed product in the actual printing is evaluated by verifying the effect of the printing simulation data. The effect verification includes the following aspects: evaluating whether the support structure is unstable or the bonding between the model layers is not firm during the printing process. By comparing with the design model, verify whether there are problems such as dimensional deviation and shape deformation during the printing process. Verify that the print time estimate generated by the simulation meets the actual production requirements and that the required materials are economically feasible. The results of the effect verification will generate personalized product effect verification data, which contains various performance indicators of the product in the simulation, such as shape accuracy, material waste, printing time, etc. The personalized product effect verification data is analyzed through dedicated defect detection algorithms (such as computer vision-based detection technology or 3D scanning technology). These inspections include: checking whether there are cracks, bubbles, interlayer detachment, etc. on the surface. Identify underprinting or missing parts in the simulation, such as the failure of the material to completely fill certain areas. Detect the structural integrity of the model, such as whether there are weak areas that cause collapse during the printing process or unstable support structures. Using advanced automated detection tools and 3D scanners, compare the simulation results with the actual model to generate product printing defect detection data. Use defect detection data for detailed defect location. This step will mark and accurately locate each defect area in the product model through coordinate mapping and image processing technology. For example, it is found that surface defects occur in a specific location, or gaps or unevenness in the printing process affect product quality. Through the 3D visualization tool, the detected defective areas are highlighted in the 3D model, and product defect location data is generated. These data can provide an important basis for subsequent repair and optimization. According to the product defect location data, the material of the defective areas in the model is optimized. For example, if there is poor interlayer adhesion in some areas, you can choose enhanced printing materials or adjust the extrusion rate of the material to solve it; if cracks appear, you can use higher strength materials for printing.Based on the defect location data, different types of printing materials are selected for different areas through the material selection optimization algorithm, or the physical properties of the material (such as hardness, elasticity, etc.) are adjusted according to the actual use requirements. Through these adjustments, personalized 3D printing product material adjustment data is generated to ensure the optimization of the printing results in terms of mechanical properties, durability and appearance. Using virtual reality (VR) technology, the 3D model with material adjustment is enhanced and displayed in a virtual reality environment. This can be presented to users through a VR helmet or a 3D display to ensure that they can intuitively see the effect of the design adjustment. Through the interactive interface in the virtual reality environment, users can rotate, zoom in, zoom out and view every detail of the 3D printed product. This interface can also include real-time material change simulation, allowing users to view the effects of different materials and structural optimizations in real time. At this stage, users can provide instant feedback to further improve the design. Finally, the final design data is generated based on the product design visualization interface enhanced by virtual reality and is ready for actual 3D printing operations.

Claims

1. A 3D printing product personalized design method based on a 3D scanning human body model, characterized in that: The following steps are involved: Step S1: Acquire human body three-dimensional scanning data and human body composition data; Perform movable joint analysis on human body 3D scanning data to generate human body movable joint data; Based on the data of movable joints of the human body, a distributed three-dimensional model is modeled on the three-dimensional scanning data of the human body to generate a three-dimensional model of the human body; Step S1 includes the following steps: Step S11: obtaining three-dimensional scanning data of a human body; obtaining human body composition data using a body composition calculation formula; Step S12: performing data preprocessing on the human body three-dimensional scanning data to generate standard human body three-dimensional scanning data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization; Step S13: performing movable joint analysis on the standard human body three-dimensional scanning data to generate human body movable joint data; performing human body part division on the standard human body three-dimensional scanning data based on the human body movable joint data to generate human body part division data; Step S14: performing distributed 3D modeling on the standard human body 3D scanning data by using the human body part division data to generate a human body 3D model; Step S2: Based on the 3D printing technology, an initial human body fitting product design is performed on the human body three-dimensional model to obtain initial 3D printing product parameter data; the human body composition data is used to perform posture coordination analysis on the human body three-dimensional model to generate human body coordination data; the human body coordination data is imported into the initial 3D printing product parameter data to adjust the fitting morphological parameters to generate 3D printing product visualization data; Step S2 includes the following steps: Step S21: performing an initial human body fitting product design on the human body three-dimensional model based on 3D printing technology to obtain initial 3D printing product parameter data; Step S22: using the human body composition data to perform posture coordination analysis on the human body three-dimensional model to generate human body posture coordination data; extracting part morphological features of the human body three-dimensional model according to the human body posture coordination data to obtain part morphological feature data; Step S23: adjusting the product morphology parameters of the initial 3D printed product parameter data by using the part morphology feature data to generate 3D printed product morphology parameter adjustment data; adjusting the product morphology parameters of the initial 3D printed product parameter data by using the part morphology feature data includes: Defining key nodes of the body contour of the three-dimensional human body model and generating key node data of the body contour; dividing the model surface mesh of the three-dimensional human body model based on the key node data of the body contour and generating model surface mesh data; Importing the body part morphological feature data into the human body three-dimensional model for body composition data mapping to generate body composition mapping data; using the body composition mapping data to perform body composition region association on the model surface mesh data to generate body composition region association data; Performing mesh surface deformation analysis on the body component region association data to generate mesh surface deformation data; performing mesh node adjustment on the body component region association data according to the mesh surface deformation data to generate mesh part contour node adjustment data; The printing level in the initial 3D printing product parameter data is adjusted by adjusting the mesh part contour node data to generate 3D printing product morphological parameter adjustment data, wherein the printing level adjustment includes muscle layer adjustment and skin layer adjustment; Step S24: simulating the product fit of the human body three-dimensional model by using the 3D printing product morphological parameter adjustment data, thereby generating product fit simulation data; and performing three-dimensional visualization of the 3D printing product morphological parameter adjustment data based on the product fit simulation data, thereby generating 3D printing product visualization data; Step S3: collecting user feedback on the 3D printed product visualization data to obtain user feedback data; modifying the changed part parameters of the 3D printed product visualization data according to the user feedback data, thereby generating a local part change model; replacing the local part change model with the 3D printed product visualization data, thereby generating personalized 3D printed product visualization data; Step S4: performing printing simulation defect location on the personalized 3D printed product visualization data to generate product defect location data; adjusting the printing material of the personalized 3D printed product visualization data according to the product defect location data to generate personalized 3D printed product material adjustment data; performing virtual reality enhancement on the personalized 3D printed product visualization data based on the personalized 3D printed product material adjustment data to generate a personalized 3D printed product design visualization interface to execute the 3D printed product personalized design operation.

2. The method for personalized design of 3D printed products based on a 3D scanning human body model according to claim 1, characterized in that: The formula for body composition calculation in step S11 is as follows: In the formula, Expressed as lean body mass, Expressed as the maximum measurement frequency, Expressed as the impedance weighting coefficient, Represents the human body at frequency The impedance value below Expressed as the height weighting coefficient, is the height of the individual, Expressed as the weight-frequency weighting coefficient, is the weight of the individual, Expressed as the age weighted coefficient, is represented as an exponential decay term of age, is the individual age, Expressed as an exponent, Expressed as the age exponential decay coefficient.

3. The method for personalized design of 3D printed products based on 3D scanning human body model according to claim 1, characterized in that: Modeling a distributed 3D model of standard human 3D scan data by dividing human body parts includes the following steps: Calculating the area of ​​human body parts to obtain area data; segmenting the standard human body three-dimensional scan data based on the area data to generate human body part area segmentation data, wherein the human body part area segmentation data includes main part area segmentation data and secondary part area segmentation data; Assigning a high modeling priority to the main part region segmentation data and a low modeling priority to the secondary part region segmentation data, thereby obtaining part region modeling priority data, and performing distributed computing node allocation on the human body part region segmentation data according to the part region modeling priority data, thereby generating distributed region modeling data; Perform local modeling on the distributed regional modeling data to generate a local three-dimensional model of the human body part; confirm the part connection points of the local three-dimensional model of the human body part to obtain the part connection center point data; and splice the local three-dimensional model of the human body part according to the part connection center point data to generate a three-dimensional model of the human body.

4. The method for personalized design of 3D printed products based on 3D scanning human body model according to claim 3, characterized in that: Confirmation of connection points of local 3D models of human body parts includes: Extracting the part boundary point set from the local three-dimensional model of the human body part to obtain the part boundary point set; performing boundary detection on the part boundary point set to generate potential connection point data of the part boundary; The distance between the boundary points of adjacent parts of the local three-dimensional model of the human body parts is calculated by using the potential connection point data of the boundary of the parts to obtain the distance data of the boundary points of adjacent parts; the distance data of the boundary points of adjacent parts is compared with the preset standard boundary point distance threshold, and when the distance data of the boundary points of adjacent parts is less than or equal to the preset standard boundary point distance threshold, the overlapping boundary point area is screened based on the distance data of the boundary points of adjacent parts to obtain the overlapping boundary point area data of adjacent parts; The data of the overlapping boundary points of adjacent parts are distributed with part connection points to generate the spatial distribution data of the part connection points; the coordinates of the center points of the connected areas of the overlapping boundary points of adjacent parts are calculated through the spatial distribution data of the part connection points to generate the data of the part connection center points.

5. The method for personalized design of 3D printed products based on 3D scanning human body model according to claim 1, characterized in that: Step S24 includes the following steps: Step S241: performing contact area recognition on the 3D printed product morphology parameter adjustment data and the human body three-dimensional model to obtain contact area recognition data; performing contact surface extraction on the 3D printed product morphology parameter adjustment data according to the contact area recognition data to obtain product-human body contact surface data; Step S242: performing contact surface distance calculation on the product-human body contact surface data to generate product-human body contact surface distance data; performing contact surface mechanics simulation on the product-human body contact surface distance data to generate contact surface mechanics simulation data; performing fit analysis based on the contact surface mechanics simulation data to generate product fit simulation data; Step S243: convert the product fit simulation data into a heat map to generate a product fit heat map; use the product fit heat map to three-dimensionally visualize the 3D printed product morphological parameter adjustment data to generate 3D printed product visualization data.

6. The method for personalized design of 3D printed products based on 3D scanning human body model according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: collecting user feedback on the 3D printing product visualization data to obtain user feedback data; extracting semantic information from the user feedback data to obtain user feedback semantic information data; Step S32: extracting product change information from the 3D printed product visualization data according to the user feedback semantic information data to obtain product change information data; modifying the changed part parameters of the 3D printed product visualization data based on the product change information data, thereby generating a local part change model; Step S33: Replace the local part of the local part change model and the 3D printing product visualization data, so as to generate personalized 3D printing product visualization data.

7. The method for personalized design of 3D printed products based on 3D scanning human body model according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing printing simulation on the personalized 3D printed product visualization data to generate personalized product printing simulation data; performing effect verification on the personalized product printing simulation data to generate personalized product effect verification data; Step S42: performing defect detection on the personalized product effect verification data to generate product printing defect detection data; performing defect location on the personalized 3D printed product visualization data using the product printing defect detection data to generate product defect location data; Step S43: adjusting the printing material of the personalized 3D printed product visualization data according to the product defect location data, thereby generating personalized 3D printed product material adjustment data; performing virtual reality enhancement on the personalized 3D printed product visualization data based on the personalized 3D printed product material adjustment data, thereby generating a personalized 3D printed product design visualization interface to execute the 3D printed product personalized design operation.

Images